Q5_1 GGUF models

A GGUF quantization format. Lower numbers mean smaller files and more quality loss. 17701 models have a Q5_1 file. Sizes run from 1M to 1030B parameters. The longest trained context is 4194304K tokens.

Most downloadedNewestLargestLongest contextSmallest
LL
LLaMA2 13B Erebus v3
Llama · KoboldAI
Params13B
Context4K
Q4_K_M7.9 GB
GGUF
QW
Qwen3Guard Gen 0.6B
Qwen · QuantFactory
Params752M
Context32K
Q4_K_M0.5 GB
Reasoning
DO
L3 OVA Test 8B
Domain · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
Roleplay
QW
Replete LLM V2.5 Qwen 14b
Qwen · RichardErkhov
Params14.8B
Context32K
Q4_K_M9.0 GB
Tool use
OU
OuteTTS 0.3 500M
Outetts · BricksDisplay
Params85M
Context—
Q4_K_M0.1 GB
GGUF
TL
tlphams solar 10.7b merged v0.1
Tlphams · RichardErkhov
Params10.7B
Context4K
Q4_K_M6.5 GB
GGUF
LL
ArliAI Llama 3 8B Formax v1.0
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Codestral-22B-v0.1
Mistral · SanctumAI
Params22.2B
Context32K
Q4_K_M13.3 GB
Coding
DI
Diffusion Models
Diffusion · f5aiteam
Params11.9B
Context—
Smallest6.8 GB
GGUF
QW
Qwen3.5 9B
Qwen · titan0115
Params8.95B
Context256K
Q4_K_M5.6 GB
ReasoningTool use
GE
Gemma 2 2b It
Gemma · RichardErkhov
Params2.61B
Context8K
Q4_K_M1.7 GB
GGUF
QW
Holo2-30B-A3B
Qwen · Mungert
Params30.5B
Context256K
Q4_K_M19.0 GB
ReasoningTool useVision
MA
MadKFC MergedCPsyModel
Madkfc · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
Tool use
LL
OneLLM Doey V1 Llama 3.2 3B Instruct
Llama · QuantFactory
Params3.61B
Context128K
Q4_K_M2.2 GB
Tool use
SK
SkyReels V2 DF 14B 720P
Skyreels · ThePun1sher
Params14.3B
Context—
Q4_K_M9.7 GB
GGUF
FL
FLAMA 0.5 3B
Flama · xaviviro
Params3.43B
Context2K
Q4_K_M2.6 GB
GGUF
FA
Falcon H1 Tiny Coder 90M
Falcon · tiiuae
Params108M
Context256K
Q4_K_M0.1 GB
Coding
HU
HunyuanVideo Avatar GGUF Experiment
Hunyuanvideo · lym00
Params13B
Context—
Q4_K_M8.0 GB
GGUF
NO
notHumpback-Myx
Nothumpback · RichardErkhov
Params3.21B
Context128K
Q4_K_M2.0 GB
GGUF
HA
Hathor Tahsin L3 8B v0.85
Hathor · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GI
GigaChat3-10B-A1.8B
Gigachat · Mungert
Params10.7B
Context256K
Q4_K_M6.7 GB
Tool use
LL
scandukuri llama3 8b stargate m1
Llama · RichardErkhov
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
GE
Gemma 2b It
Gemma · RichardErkhov
Params2.51B
Context8K
Q4_K_M1.6 GB
GGUF
QW
Qwen2.5 7B Instruct
Qwen · ThomasBaruzier
Params7.62B
Context32K
Q4_K_M4.7 GB
Tool use
DI
distilgpt2
Distilgpt · RichardErkhov
Params121M
Context1K
Q4_K_M0.1 GB
GGUF
LL
Llama 3 8B Web
Llama · QuantFactory
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
OP
openchat-3.6-8b-20240522
Openchat · crusoeai
Params8.03B
Context8K
Q4_K_M4.9 GB
GGUF
MI
Mistral 7B Instruct DPO
Mistral · QuantFactory
Params7.24B
Context32K
Q4_K_M4.4 GB
GGUF
LE
Leia Swallow 7b
Leia · RichardErkhov
Params6.83B
Context4K
Q4_K_M4.1 GB
GGUF
LL
Meta-Llama-3-13B-Instruct
Llama · LiteLLMs
Params13.9B
Context8K
Q4_K_M8.4 GB
GGUF

Other quants

Keep browsing